Type ProximalGradientDescentOptimizer
Namespace tensorflow.train
Parent Optimizer
Interfaces IProximalGradientDescentOptimizer
Optimizer that implements the proximal gradient descent algorithm. See this [paper](http://papers.nips.cc/paper/3793-efficient-learning-using-forward-backward-splitting.pdf).
Methods
Properties
Public static methods
ProximalGradientDescentOptimizer NewDyn(object learning_rate, ImplicitContainer<T> l1_regularization_strength, ImplicitContainer<T> l2_regularization_strength, ImplicitContainer<T> use_locking, ImplicitContainer<T> name)
Construct a new proximal gradient descent optimizer.
Parameters
-
objectlearning_rate - A Tensor or a floating point value. The learning rate to use.
-
ImplicitContainer<T>l1_regularization_strength - A float value, must be greater than or equal to zero.
-
ImplicitContainer<T>l2_regularization_strength - A float value, must be greater than or equal to zero.
-
ImplicitContainer<T>use_locking - If True use locks for update operations.
-
ImplicitContainer<T>name - Optional name prefix for the operations created when applying gradients. Defaults to "GradientDescent".